© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33039
    Prev
    Next
    INDEX
    Explanations

    except bank holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĽ·
    -0.10
     móc
    -0.10
    æŃ£åĵģ
    -0.09
    太太
    -0.09
    亲çĪ±
    -0.09
     downgrade
    -0.09
    hare
    -0.09
    åīį段æŶéĹ´
    -0.09
    æĪĸå°Ĩ
    -0.09
    åľ¨æĹ¥æľ¬
    -0.08
    POSITIVE LOGITS
    ä¸įéĢļ
    0.10
    ä¾ĭå¤ĸ
    0.09
     except
    0.08
    agg
    0.08
    å¼¥
    0.08
    éĻ¤å¤ĸ
    0.08
    mere
    0.08
    æıIJåīį
    0.08
     Exceptions
    0.08
     lcm
    0.07
    Activations Density 0.031%

    No Known Activations